Deep learning Chorale prelude | Fresco Play

Question 1: Data Collected from Survey results is an example of ______

Answer: structured data

Question 2: Gradient at a given layer is the product of all gradients at the previous layers.

Answer: True

Question 3: Name the component of a Neural Network where the true value of the input is not observed.

Answer: Hidden layer

Question 4: _______________ is a Neural Nets way of classifying inputs.

Answer: FP

Question 5: Prediction Accuracy of a Neural Network depends on _______________ and ______________.

Answer: weight and bias

Question 6: Recurrent Networks work best for Speech Recognition.

Answer: True

Question 7: In a Neural Network, all the edges and nodes have the same Weight and Bias values.

Answer: False

Question 8: Recurrent Neural Networks are best suited for Text Processing.

Answer: True

Question 9: Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological Neuron.

Answer: True

Question 10: The rate at which cost changes with respect to weight or bias is called _________

Answer: Gradient

Question 11: GPU stands for ________

Answer: Graphics Processing Unit

Question 12: What is the difference between the actual output and generated output known as?

Answer: Cost

Question 13: A Shallow Neural Network has only one hidden layer between Input and Output layers.

Answer: True

Question 14: _____________ is a recommended Model for Pattern Recognition in Unlabeled Data.

Answer: auto

Question 15: Process of improving the accuracy of a Neural Network is called _______________.

Answer: Training

Question 16: Restricted Boltzmann Machine expects the data to be labeled for Training.

Answer: False

Question 17: What is the best Neural Network Model for Temporal Data?

Answer: Recurrent Neural Network

Question 18: How do RNTS interpret words?

Answer: vector

Question 19: Recurrent Network can input Sequence of Data Points and Produce a Sequence of Output.

Answer: True

Question 20: A Deep Belief Network is a stack of Restricted Boltzmann Machines.

Answer: True

Question 21: nan

Answer: hidden

Question 22: All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other.

Answer: False

Question 23: What is the best Neural Network Model for Temporal Data?

Answer: recuurent

Question 24: What are the two layers of a Restricted Boltzmann Machine called?

Answer: Hidden and Visible Layers

Question 25: RELU stands for ________

Answer: rectified linear

Question 26: All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other.

Answer: False

Question 27: Why is the Pooling Layer used in a Convolution Neural Network?

Answer: dimension

Question 28: All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other.

Answer: False

Question 29: What does LSTM stand for?

Answer: Long Short Term Memory

Question 30: All the neurons in a convolution layer have different Weights and Biases.

Answer: False

Question 31: The measure of Difference between two probability distributions is know as

Answer: KL Diver

Question 32: ___________ works best for Image Data.

Answer: convultion

Question 33: Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological Neuron.

Answer: True

Question 34: Autoencoders cannot be used for Dimensionality Reduction.

Answer: False

Question 35: What is the method to overcome the Decay of Information through time in RNN known as?

Answer: Gating

Question 36: De-noising and Contractive are examples of _____________

Answer: Autoencoders

Question 37: What is the difference between the actual output and generated output known as?

Answer: cost

Question 38: ________________ models are best suited for Recursive Data.

Answer: Recursive Neural Tensor Nets

Question 39: A _______________ matches or surpases the output of an individual neuron to a visual stimuli.

Answer: Convolution

Question 40: Support Vector Machines, Naive Bayes and Logistic Regression are used for solving _______________________ problems.

Answer: Classification

Question 41: How do RNTS interpret words?

Answer: Vector Representations

Question 42: Autoencoders are trained using ___________________

Answer: Back Propagation

Question 43: A _________________ matches or surpasses the output of an individual neuron to a visual stimuli.

Answer: Convolution

Question 44: All the Visible Layers in a Restricted Boltzmann Machine are connected to each other.

Answer: False